Systems and Soft Computing最新文献

{"title":"Quantitative analysis of MIDI sequence editors for electronic music production","authors":"Xianying Zhou","doi":"10.1016/j.sasc.2025.200292","DOIUrl":"10.1016/j.sasc.2025.200292","url":null,"abstract":"<div><div>The rapid development of digital technology provides new tools and methods for electronic music creation. MIDI (Musical Instrument Digital Interface) sequence editor, as an important tool, is widely used in electronic music production. In this paper, the function, working principle and application value of MIDI sequence editor in electronic music creation are discussed by using quantitative and qualitative analysis methods. The research shows that MIDI sequence editor can input, edit and output music data by converting input signals such as computer keyboard and mouse into MIDI note signals. Its system model is composed of computer hardware (CPU, memory, sound card interface, MIDI interface, etc.), software (operating system, music synthesis software, MIDI device driver) and user interface (text box, button, slider, menu, canvas, etc.), providing users with a complete music creation platform. From the perspective of the development of electronic music, MIDI sequence editor not only supports different styles of music creation such as avant-garde electronics, electronic pop, electronic dance music, but also has powerful functions, including note input, editing, track creation, synthetic output, rhythm perception and effect processing. For example, it can identify the duration and spacing of notes, automatically set the beat point and adjust the duration of notes to enhance the sense of rhythm of music, while supporting volume, pitch, reverberation, echo and other effects processing, providing a rich means of expression for music creation. The results of quantitative analysis show that the electronic music composed by MIDI sequence editor has high sound quality (note matching degree of 82 %) and real-time audio and video interaction ability (virtual instrument playing matching degree of 86 %). In addition, qualitative analysis shows that MIDI sequence editor has the advantages of high flexibility, high accuracy, repeatable editing, visual operation and good compatibility. Users can easily create and edit various types of music works, achieve accurate control of music elements, and modify and improve them at any time. At the same time, its intuitive user interface and good compatibility also lower the threshold of music production. To sum up, MIDI sequence editor, with its powerful functions and advantages, has become an indispensable tool for electronic music production, providing efficient and convenient tools and methods for music creation. In the future, there is still room for further improvement in music expression, performance optimization, rhythm perception and effect processing.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"7 ","pages":"Article 200292"},"PeriodicalIF":0.0,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144147513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-camera association tracking algorithm for pedestrian target based on difference image","authors":"Shuai Ren","doi":"10.1016/j.sasc.2025.200282","DOIUrl":"10.1016/j.sasc.2025.200282","url":null,"abstract":"<div><div>The current pedestrian target tracking algorithm (such as adjacent frame matching target tracking algorithm, deep learning YOLOv5 algorithm, etc.) ignores pedestrian foreground image segmentation, resulting in significant errors in pedestrian target tracking and insufficient tracking results. Therefore, a multi-camera association tracking algorithm for pedestrians and targets based on differential images is designed. Multi-camera devices are used to collect pedestrian video sequence images, and the key frame difference image sample set is extracted. The initial background of the pedestrian image is modeled, and the foreground image is differentially segmented to construct the initial model of the differential image. The DeepSORT algorithm is used to complete the multi-pedestrian target association. The pedestrian target obeys the Laplacian random variable probability density function, and moves according to the center position of the bounding box to ensure that the target tends to move around the starting position, and realizes the multi-camera association tracking. The research method achieved maximum MOTA and MOTP values of 18.87 % and 99.22 % under different experimental times, demonstrating good association tracking ability. Moreover, the maximum comprehensive index of multiple pedestrian target association results approached 100 %, while the minimum value far exceeded 95 %. The tracking comprehensiveness and trajectory interruption rate of the research method were 98 % and 1.2 %, respectively, which were significantly better than other comparison algorithms. The processing speed reached 25FPS, effectively balancing computational efficiency. The experimental results verify that the proposed algorithm has ideal application effects.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"7 ","pages":"Article 200282"},"PeriodicalIF":0.0,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144130894","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application analysis of improved LeNet5 model in library management","authors":"Zhihao Zhao","doi":"10.1016/j.sasc.2025.200285","DOIUrl":"10.1016/j.sasc.2025.200285","url":null,"abstract":"<div><div>Nowadays, libraries have been able to achieve intelligent book positioning and borrowing. However, the book disorder affects user experience and increase management burden. A book disorder recognition system based on LeNet5 optimization model is proposed to address this issue. Firstly, the overall recognition system is designed, including a wireless radio frequency identification module, a pre-processing module, an image recognition module, and a post-processing module. The image recognition module is the key to the model. The first two modules are the foundation of this module. Therefore, the Canny operator is used to design basic modules. Subsequently, in the TensorFlow deep learning framework, a recognition system based on the LeNet5 model is designed. The whitening is used to further improve model performance. In the experimental analysis, the results showed that the recognition accuracy of the model reached 97.97 %, with an average time of 182 s. Therefore, the character recognition system based on optimized LeNet5 network proposed in the study can help libraries achieve intelligent book shelving management.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"7 ","pages":"Article 200285"},"PeriodicalIF":0.0,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144147514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Online English teaching resource recommendation method design based on LightGCNCSCM","authors":"Jing Tang","doi":"10.1016/j.sasc.2025.200294","DOIUrl":"10.1016/j.sasc.2025.200294","url":null,"abstract":"<div><div>With the explosive growth of online English teaching resources, how to achieve personalized and high-quality resource recommendations has become a key issue that needs to be urgently solved. Existing methods have significant limitations in aspects such as cold start scenarios, semantic feature fusion, and the balance between computational efficiency and recommendation quality. The research proposes an online English teaching resource recommendation method. The local and global features of the user-resource interaction graph are captured through Lightweight graph convolutional networks, and the resource semantic vectors are extracted in combination with the content-based similarity calculation model. This can synergistically optimize behavior structure and content semantics. Experiment results show that this method significantly improves the recommendation quality in the cold start scenario. It balances the novelty of recommendation results and user preference matching through a dynamic weight allocation mechanism, while maintaining relatively low computational complexity. This method provides an efficient and robust personalized recommendation solution for online education platforms.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"7 ","pages":"Article 200294"},"PeriodicalIF":0.0,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144105470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Area-based face curve characteristic analysis to recognize Multimodal 2D/3D monozygotic twins using Simpson’s rule and Machine Learning","authors":"Gangothri Sanil ,&nbsp;Krishna Prakasha ,&nbsp;Srikanth Prabhu ,&nbsp;Vinod C. Nayak","doi":"10.1016/j.sasc.2025.200267","DOIUrl":"10.1016/j.sasc.2025.200267","url":null,"abstract":"<div><div>Recent advances in face recognition have achieved high accuracy in identifying individuals. However, distinguishing identical twins remains challenging due to their substantial facial similarity. Human vision and collective intelligence suggest that the lower face margin curve is the most distinctive region for differentiating twins. Hence, this proposed technique measures and compares the face curve characteristics of the identical twins by calculating the area of the face curve using Simpson’s rules from values of the ordinates about the face’s vertical axis along the nose point. To more accurately identify and analyze the facial differences and compare the twin faces, the resulting area-based score is then used as input to various machine learning algorithms such as Extreme gradient boosting (XGBoost), Adaptive Boosting (AdaBoost) classifiers, Random Forest (RF) classifiers, Light Gradient Boosting Model(LGBM), and Extra Tree Classifier(ETC) classifiers, etc. The datasets ND-TWINS and 3D TEC produce encouraging classification rates of 94%, and 86%. In this paper, we discuss the impact of Simpson’s rule on categorical data and demonstrate its effects on AI and ML application scenarios.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"7 ","pages":"Article 200267"},"PeriodicalIF":0.0,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144072764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correlation analysis between multi-category design arts based on principal component analysis model","authors":"Lili Wang","doi":"10.1016/j.sasc.2025.200286","DOIUrl":"10.1016/j.sasc.2025.200286","url":null,"abstract":"<div><div>In order to explore the correlation between multi-category design arts, this paper combines principal component analysis model and intelligent art image recognition algorithm to conduct correlation analysis between multi-category design arts. Moreover, this paper constructs the art design model through the art image information recognition algorithm, and solves the one-dimensional transient art image information transfer equation under the diffuse reflection boundary condition. Simultaneously, this paper analyzes the influence of different albedos on the hemispherical reflectance and hemispherical transmittance. In addition, this paper solves the transient artistic image information transfer between double-layer plates with different parameters, considers the case that the refractive index inside the medium is greater than 1, and gives a corresponding calculation example. The research above reveals a strong correlation between various categories of design arts, highlighting the multifaceted role that artistic design can play.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"7 ","pages":"Article 200286"},"PeriodicalIF":0.0,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144089587","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hybrid evolutionary algorithm for maximizing medical equipment supply during pandemic✰","authors":"C. D James ,&nbsp;Sandeep Mondal","doi":"10.1016/j.sasc.2025.200275","DOIUrl":"10.1016/j.sasc.2025.200275","url":null,"abstract":"<div><div>Inadequate capacity and delayed delivery of electronic life support equipment was a major impediment in saving human lives during COVID-19. Capital intensive mass customised electronics and semiconductor manufacturing formed critical raw material for the same. Targeted efficiency achievement fails when variety and flexibility are prioritised in chip production. Digital manufacturing involves artificial intelligence for planning and autonomous execution with robotic hi-tech machines. However, large number of controlling factors fluctuate at extreme levels in the manufacturing environment leading to capacity shrinkage risk of these machines. In this paper, we make use of a simulation-based model to demonstrate solution to this problem because experimental setups involve high cost and delivery risks.</div><div>Firstly, we identified thirty-one factors that affect hi-tech machine efficiency. Of these, thirteen factors were shortlisted through confidential voting by the industry experts to mirror the actual challenges during pandemic. We developed a model, and simulated problem scenarios for shortlisted factors at three levels. Design of experiments was performed using Taguchi based orthogonal arrays. Signal to noise ratios were used to determine the main effects and robust combination of factor levels for high efficiency. Significant factors were identified from ANOVA for variance-reduction based robustness design.</div><div>A better solution was created using a learning-based fruit fly optimization algorithm and further using a hybrid fruit fly grasshopper leap optimization. This algorithm successfully supported the high customization scenario for manufacturing efficiency during pandemic for any pre-set parameters by accelerating learning cycles. In addition, a multifactor particle swarm optimization was also performed for managing dynamic changes in all 31 factors together and the results were compared with previous techniques. The managerial implications and conclusion are explained for the benefit of the electronics industry and academia.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"7 ","pages":"Article 200275"},"PeriodicalIF":0.0,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143935150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Classification of landscape architecture design based on dual-channel attention improved FCN","authors":"Zhongyu Zhou","doi":"10.1016/j.sasc.2025.200280","DOIUrl":"10.1016/j.sasc.2025.200280","url":null,"abstract":"<div><div>Landscape architecture design integrates natural and artificial landscapes, and needs to accurately categorize diverse landscape elements. To solve the problems of low efficiency and high subjectivity of traditional design, the study proposes an improved fully convolutional network model that combines the U-Net structure, multi-scale hopping connection network, and dual-channel attention mechanism to enhance the ability of detail capture and feature fusion. The experimental results show that the model achieves the highest classification recall of 0.92, the shortest inference time of 0.17 s, the precision of 92.96 %, 93.97 % and 92.94 % on vegetation, sky and building categories, respectively, and the feature extraction is stable with good robustness in pixel value interval. The results validate the efficiency and adaptability of the model in complex landscape scenes and provide effective support for landscape design intelligence.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"7 ","pages":"Article 200280"},"PeriodicalIF":0.0,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143932198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fault diagnosis method of telecom cloud platform based on deep CNN model","authors":"Qingpu Hu,&nbsp;Jian Hu","doi":"10.1016/j.sasc.2025.200273","DOIUrl":"10.1016/j.sasc.2025.200273","url":null,"abstract":"<div><div>In response to the problem of fault location caused by massive alarm logs in the complex architecture of telecom cloud platforms, this study proposes a time-frequency image recognition model (WCNN) based on depthwise separable small convolution kernels, which replaces traditional pooling layers to achieve efficient feature extraction. We propose a time-frequency image recognition model based on depthwise separable small convolution kernels to address the issue of information loss caused by improper handling of fuzzy features in traditional pooling methods. The experimental results show that in extreme noise environments with a signal-to-noise ratio of -4 dB, the WCNN model achieves a recognition accuracy of 90 %, significantly better than FFT-SVM (&lt;60 %), FFT-KNN (&lt;60 %), FFT-BP (80 %), and FFT-DNN (80 %). In addition, under low noise conditions (signal-to-noise ratio&gt;6), the accuracy of the WCNN model is further improved to 99.3 %, and the model complexity is reduced by 42 % compared to traditional convolutional neural networks, resulting in a 30 % increase in computational efficiency. The research has verified the anti-interference ability and feature preservation advantages of the WCNN model in strong noise environments, providing an efficient solution for fault diagnosis in telecommunications cloud platforms.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"7 ","pages":"Article 200273"},"PeriodicalIF":0.0,"publicationDate":"2025-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143935033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Research on cloud computing network security mechanism and optimization in university education management informatization based on OpenFlow","authors":"Xiufang Dong,&nbsp;Yun Xie","doi":"10.1016/j.sasc.2025.200225","DOIUrl":"10.1016/j.sasc.2025.200225","url":null,"abstract":"<div><div>With the widespread application of cloud computing technology in higher education management, network security issues have become a key factor restricting its further development. According to the latest data, university network attack incidents are on the rise yearly, with attacks targeting cloud computing environments accounting for as much as 60 %. Cloud computing environments must ensure comprehensive security of their hardware infrastructure, virtual resources, computing power, software platforms, applications, and data. To ensure the security of related components, it is necessary to start from the physical layer to the virtual resource layer and the service layer. Use a variety of network technologies, including network area boundary access control, intrusion prevention, security audit, centralized management, identity verification, access control, implement data security measures, establish backup and recovery mechanisms, do a good job in residual information protection, ensure the credibility of the cloud environment, strengthen virtualization security, and prevent malicious code. This study optimized the university education management informatization network security mechanism based on OpenFlow. By comparing traditional network traffic control technologies, it is found that OpenFlow has significant advantages in flexibility, programmability, and security. Experimental data shows that cloud computing network environments using OpenFlow technology have reduced response time by 30 % when subjected to network attacks while reducing the risk of data leakage by 40 %. The analysis of research data on IT infrastructure in multiple universities found that about 70 % of university network equipment can support OpenFlow technology after upgrading.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"7 ","pages":"Article 200225"},"PeriodicalIF":0.0,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143935034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}